Predictive maintenance and process optimization are critical components in modern manufacturing systems. This paper explores the application of AI-driven predictive maintenance and machine learning techniques in optimizing manufacturing processes using sensor analytics. The proposed methodology is inspired by the "Edge-Based Predictive Maintenance for Subsonic Wind Tunnel Systems Using Sensor Analytics and Machine Learning" paper, which emphasizes the use of real-time sensor data, machine learning algorithms, and edge computing for effective predictive maintenance. By implementing this methodology in manufacturing systems, the paper highlights how machine learning models can predict machine failures, optimize process parameters, and reduce downtime. A case study focusing on a manufacturing plant’s production line is analyzed to demonstrate the effectiveness of the proposed solution.
Arafat Bin Fazle (Wed,) studied this question.